Personalized Ranking Metric Embedding for Next New POI Recommendation

Authors: Shanshan Feng, Xutao Li, Yifeng Zeng, Gao Cong, Yeow Meng Chee, Quan Yuan

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the stateof-the-art next POI recommendation methods.
Researcher Affiliation Academia 1Interdisciplinary Graduate School, Nanyang Technological University, Singapore, sfeng003@e.ntu.edu.sg 2School of Computer Engineering, Nanyang Technological University, Singapore, {lixutao@, gaocong@, qyuan1@e.}ntu.edu.sg 3School of Computing, Teesside University, UK, Y.Zeng@tees.ac.uk 4School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore, ymchee@ntu.edu.sg
Pseudocode Yes Algorithm 1: PRME
Open Source Code No The paper does not provide an explicit statement or link to the open-source code for the described methodology.
Open Datasets Yes We use two publicly available datasets. The first dataset is the Four Square check-ins within Singapore [Yuan et al., 2013] while the second one is the Gowalla check-ins dataset within California and Nevada [Cho et al., 2011].
Dataset Splits Yes For the one-year check-ins data, we use the check-ins in the first 10 months as training set, the 11th month as tuning set, and the last month as test set.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments.
Software Dependencies No The paper mentions software like 'Matlab' in related work (Table 2 in some versions, but not this PDF), but does not specify any software dependencies with version numbers for their own experimental setup.
Experiment Setup Yes In the experiments, we use the two datasets introduced in Section 3. For the one-year check-ins data, we use the check-ins in the first 10 months as training set, the 11th month as tuning set, and the last month as test set. We exploit two wellknown measure metrics [Yuan et al., 2013], namely Precision@N and Recall@N (denoted by Pre@N and Rec@N respectively). Given a user and his current location, we use the next check-in in successive τ hours as the ground truth. The time window threshold τ is set at 6 hours following [Cheng et al., 2013]. Based on the tuning set, the number of dimensions is set at K = 60, learning rate γ = 0.005, regularization term λ = 0.03 and component weight α = 0.2.